Full-text search across 61874 articles. Combine with topic and date filters; results sorted by relevance.
On July 16, 2024, developer Nick shipped the first build of Repo Prompt, a tool designed to automate copy-pasting code into AI models, after recognizing that early coding tools struggled with context windows and reliable…
Xint's article explains that AI-native code scanners face unpredictable costs because linear increases in code lines can cause exponential increases in token consumption, making it difficult for security teams to forecas…
A senior engineer at a developer tooling company argues that the question of which AI coding tool will win is fundamentally flawed, as the market is fragmenting into three distinct segments: pro-dev, enterprise low-code,…
Cloudflare's Code Mode MCP server exposes its entire API of more than 2,500 endpoints in roughly 1,000 tokens by offering just two operations — search for an API surface and execute code against the discovered typed API …
The C# team is redesigning the `unsafe` keyword to enforce stricter memory safety contracts, expanding it from marking pointer usage to any code the compiler cannot validate as safe. This change, planned as a C# 16 featu…
Daniel Doubrovkine, a developer and former AWS principal engineer, argues that LeetCode-style coding interviews should be eliminated in the age of AI, citing his own failure to implement a basic binary tree diameter algo…
Ken Thompson's 1984 ACM Turing Award lecture, "Reflections on Trusting Trust," published in Communications of the ACM volume 27, issue 8, pages 761–763, demonstrated that a malicious compiler can insert a backdoor into t…
A new architectural analysis reveals that production AI agent systems are dominated by operational infrastructure rather than AI decision logic, with Claude Code's leaked source code showing only about 1.6% of its codeba…
Developer Mohamed Amine Hamdi released jobhunt, a set of eleven skills for coding agents including Claude Code that tailors a CV to a specific job posting, with the code published on GitHub and free for personal job sear…
A weekly OSINT curation roundup highlights new open-source tooling for AI coding agents, including Motifcode, a terminal coding agent whose tool set and prompt layout are derived from measured properties of the Motif-3 m…
Stack Overflow's 16th Developer Survey, drawing more than 30,000 respondents over seven weeks, found that 73% of developers who use AI coding assistants or agents use them daily and 62% of all respondents view AI at leas…
Anthropic announced that Claude autonomously formalized a complete proof of Fermat's Last Theorem in Lean 4, generating roughly 13.4 million lines of code and 29,500 intermediate theorems in 11 days, completing Freek Wie…
A developer released the source code of their website, jrm-code-public, on GitHub with secrets redacted, to demonstrate the kind of Lisp code generated by an LLM. The code is more complex than a standard static site and …
Sarj.ai's CTO developed Standards, an open-source linting tool that encodes three years of code reviews into 100+ deterministic rules to enforce code quality in AI-generated code. The tool runs in pre-commit, automatical…
A study analyzing 1,794 valid coding trajectories from a dataset of 3,843, generated by seven leading models across three coding-agent scaffolds (OpenHands, MiniSWE, and Terminus2), found that coding agents often fail du…
Chinese AI company Zhipu AI launched ZCode, an autonomous coding agent, on Wednesday, capitalizing on Anthropic's scandal over hidden code in Claude Code that tracked Chinese users. Zhipu offered free tokens and increase…
Anthropic published an essay revealing that over 80% of its production code is now written by Claude, with engineers shipping roughly eight times more code than in 2024. The essay argues that as AI automates code executi…
Z.ai (formerly ZhipuAI) launched GLM-5.2, an open text model with a 1M-token context window and up to 128K output tokens, designed for long-horizon coding agents and full-repository tasks. The model uses IndexShare spars…
On June 4, 2026, Jeremy D. Miller, creator of the .NET Wolverine framework, published a blog post arguing that vertical slice architecture makes codebases more compatible with AI coding assistants by reducing per-feature…
AiLock released a new encryption tool that keeps source code encrypted on disk while allowing developers to run Python programs normally in memory. The tool encrypts files in place so AI coding assistants and file-readin…